Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/bonifatius94/myscrape/dev-workflownpx skills add Bonifatius94/myscrape --skill dev-workflowgit clone --depth 1 https://github.com/Bonifatius94/myscrapeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00053 | $0.00542 |
| Opus 5 | $0.00026 | $0.00271 |
| Sonnet 5 | $0.00011 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
dev-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
myscrape-go dev workflow
Operating rules for this repository. Follow them by default.
Tooling: stable only
- Standard Go toolchain: gofmt, go vet, go test, go build. Go 1.26+.
- Use stable, widely-used libraries. Isolate anything unstable (HTTP, the headless
browser) behind an interface and mock it in tests — see the
Doerseam (internal/httpx) and theRendererseam (internal/fetch). Tests run offline; no network, no GPU.
TDD loop (mandatory for logic)
- 🔴 Write a failing test first; run it; confirm it fails for the right reason (in Go, a missing symbol = a compile failure = red).
- 🟢 Minimum code to pass; run; confirm green.
- ♻️ Refactor; tests stay green.
Inject clock/sleep/rng so time-dependent code (rate limiter, backoff) is
deterministic — see internal/ratelimit and internal/retry.
The gate
Enable the hook once: git config core.hooksPath .githooks. It runs gofmt + go
vet + go test on every commit (CI mirrors it). Don't bypass it. For stability
work also run go run ./cmd/bench (live; keep ratelimit_rate == 0).
Behavior is inherited
Operating points (8s/2s pacing, retryable statuses, BM25, circuit breaker, the
error taxonomy, effort knobs) mirror the Python reference and are evidence-backed
(specs/EXPERIMENTS.md). Don't "optimize" them without re-running the gate.
Docs & decisions
- Specs live in
specs/, user docs indocs/— never the repo root. - Record every non-trivial decision in
specs/DEVLOG.md(seelog-decision).
Checkpoints & commits
Work in small checkpoints; commit after each (commit, don't push unless asked). A checkpoint is green when gofmt is clean, vet passes, and tests pass. Imperative subject + a body explaining the why.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 44 lines · 53 tokens per session scan A 44c6d5bcda33
dev-workflow is a skill published in the GitHub repository Bonifatius94/myscrape (1 stars, last pushed 6d ago), licensed MIT. It adds 53 tokens to every session and 542 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.